---
license: mit
library_name: transformers
tags:
  - chemistry
  - cheminformatics
  - natural-products
  - smiles
---

# CLaM-NP

SMILES language models for **natural-product-likeness** scoring (CLaM-NP Score).

This repository hosts up to three causal language models, one per subfolder:

| Subfolder    | Training data | Role                          |
|--------------|---------------|-------------------------------|
| `natural`    | COCONUT       | P(x \| natural)               |
| `synthetic`  | ZINC22        | P(x \| synthetic)             |
| `general`    | ChEMBL        | P(x \| general) — stabilizer  |

Tokenizer: [`kohbanye/SmilesTokenizer_PubChem_1M`](https://huggingface.co/kohbanye/SmilesTokenizer_PubChem_1M).

## Training data

The three models are trained on a joint scaffold split: the scaffolds of all three
datasets are pooled and clustered together (ECFP4 Tanimoto >= 0.6), and each
cluster goes to a single split, so no scaffold is shared between the training data
of one dataset and the evaluation data of another. The split is built by
[`scripts/joint_split.py`](https://github.com/ohuelab/clamnp/blob/main/scripts/joint_split.py).

- `natural`: COCONUT, August 2025 release (`coconut_csv-08-2025.zip`)
- `synthetic`: 700,000 compounds drawn at random from ZINC 22. A random draw
  cannot be repeated, so the sample is deposited here as `data/zinc22_sample.smi`
  (one SMILES per line, as standardized for training).
- `general`: ChEMBL 35

## Usage

```python
from clamnp import CLaMNPScorer

scorer = CLaMNPScorer.from_pretrained()          # this repo
print(scorer.score("CC(=O)Oc1ccccc1C(=O)O"))         # CLaM-NP Score
```

Or load a single model directly:

```python
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("kohbanye/clamnp", subfolder="natural")
```